深度学习人工智能可从组织切片预测同源重组缺陷和铂类药物反应。

Deep Learning Artificial Intelligence Predicts Homologous Recombination Deficiency and Platinum Response From Histologic Slides.

机构信息

Moores Cancer Center, UC San Diego, La Jolla, CA.

Department of Cellular and Molecular Medicine, UC San Diego, La Jolla, CA.

出版信息

J Clin Oncol. 2024 Oct 20;42(30):3550-3560. doi: 10.1200/JCO.23.02641. Epub 2024 Jul 31.

DOI:10.1200/JCO.23.02641

PMID:39083703

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11469627/

Abstract

PURPOSE

Cancers with homologous recombination deficiency (HRD) can benefit from platinum salts and poly(ADP-ribose) polymerase inhibitors. Standard diagnostic tests for detecting HRD require molecular profiling, which is not universally available.

METHODS

We trained DeepHRD, a deep learning platform for predicting HRD from hematoxylin and eosin (H&E)-stained histopathological slides, using primary breast (n = 1,008) and ovarian (n = 459) cancers from The Cancer Genome Atlas (TCGA). DeepHRD was compared with four standard HRD molecular tests using breast (n = 349) and ovarian (n = 141) cancers from multiple independent data sets, including platinum-treated clinical cohorts with RECIST progression-free survival (PFS), complete response (CR), and overall survival (OS) endpoints.

RESULTS

DeepHRD predicted HRD from held-out H&E-stained breast cancer slides in TCGA with an AUC of 0.81 (95% CI, 0.77 to 0.85). This performance was confirmed in two independent primary breast cancer cohorts (AUC, 0.76 [95% CI, 0.71 to 0.82]). In an external platinum-treated metastatic breast cancer cohort, samples predicted as HRD had higher complete CR (AUC, 0.76 [95% CI, 0.54 to 0.93]) with 3.7-fold increase in median PFS (14.4 3.9 months; = .0019) and hazard ratio (HR) of 0.45 ( = .0047). There were no significant differences in nonplatinum treatment outcome by predicted HRD status in three breast cancer cohorts, including CR (AUC, 0.39) and PFS (HR, 0.98, = .95) in taxane-treated metastatic breast cancer. Through transfer learning to high-grade serous ovarian cancer, DeepHRD-predicted HRD samples had better OS after first-line (HR, 0.46; = .030) and neoadjuvant (HR, 0.49; = .015) platinum therapy in two cohorts.

CONCLUSION

DeepHRD can predict HRD in breast and ovarian cancers directly from routine H&E slides across multiple external cohorts, slide scanners, and tissue fixation variables. When compared with molecular testing, DeepHRD classified 1.8- to 3.1-fold more patients with HRD, which exhibited better OS in high-grade serous ovarian cancer and platinum-specific PFS in metastatic breast cancer.

摘要

目的

同源重组缺陷（HRD）的癌症可以从铂盐和聚（ADP-核糖）聚合酶抑制剂中获益。检测 HRD 的标准诊断测试需要分子分析，但并非普遍可用。

方法

我们使用来自癌症基因组图谱（TCGA）的原发性乳腺癌（n=1008）和卵巢癌（n=459）训练了 DeepHRD，这是一种用于从苏木精和伊红（H&E）染色组织学幻灯片预测 HRD 的深度学习平台。使用来自多个独立数据集的乳腺癌（n=349）和卵巢癌（n=141）癌症，将 DeepHRD 与四种标准 HRD 分子测试进行了比较，包括具有 RECIST 无进展生存期（PFS）、完全缓解（CR）和总生存期（OS）终点的铂类治疗临床队列。

结果

DeepHRD 预测 TCGA 中保留的 H&E 染色乳腺癌幻灯片中的 HRD，AUC 为 0.81（95%CI，0.77 至 0.85）。这一性能在两个独立的原发性乳腺癌队列中得到了证实（AUC，0.76 [95%CI，0.71 至 0.82]）。在一个外部的铂类治疗转移性乳腺癌队列中，预测为 HRD 的样本具有更高的完全 CR（AUC，0.76 [95%CI，0.54 至 0.93]），中位 PFS 增加了 3.7 倍（14.4 3.9 个月； =.0019），风险比（HR）为 0.45（ =.0047）。在三个乳腺癌队列中，根据预测的 HRD 状态，非铂类治疗结果没有显著差异，包括紫杉醇治疗转移性乳腺癌的 CR（AUC，0.39）和 PFS（HR，0.98， =.95）。通过转移学习到高级别浆液性卵巢癌，DeepHRD 预测的 HRD 样本在两个队列的一线（HR，0.46； =.030）和新辅助（HR，0.49； =.015）铂类治疗后具有更好的 OS。

结论

DeepHRD 可以直接从多个外部队列、幻灯片扫描仪和组织固定变量的常规 H&E 幻灯片中预测乳腺癌和卵巢癌中的 HRD。与分子检测相比，DeepHRD 将 1.8 至 3.1 倍更多的 HRD 患者进行分类，在高级别浆液性卵巢癌中表现出更好的 OS，在转移性乳腺癌中表现出更好的铂类特异性 PFS。